Forecasting Euro and Turkish Lira Exchange Rates with Artificial Neural Networks (ANN)

Forecasting of financial data has been a field of research since the efficiency of prediction is essential for strategical decision making. Forecasting exchange rates is not a simple task because it is influenced by many factors and linear models are not able to capture nonlinear relationships in the data. Therefore ANNs have been used in financial forecasting problems since it is capable of handling complex data. The aim of this study is to consider predictive accuracy of ANNs with normalized back propagation using the historical Euro and Turkish Lira (EUR/TRY) exchange rates. The data is obtained from CBRT (Central Bank of the Republic of Turkey) over the period 2010-2013. Several factors affect the accuracy of neural network in the implementation process. Various structures are built by changing the number of neurons, transfer functions and learning algorithms to acquire higher performance. This empirical research has been a comparative study of accuracy in different ANN architectures also in different time horizons. The results are evaluated by MSE (Mean Squared Error) values of each case and it has been found out that ANNs can closely forecast the future EUR/TRY exchange rates.